© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21589
    Prev
    Next
    INDEX
    Explanations

    aprons or apricot

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ness
    -0.12
    fred
    -0.10
    NESS
    -0.10
     trÃŃ
    -0.10
    openh
    -0.09
    ISTR
    -0.09
     пÑĢид
    -0.09
    çĦ¯
    -0.09
    æĸ¯å¡Ķ
    -0.09
    PLEX
    -0.09
    POSITIVE LOGITS
    CTS
    0.09
    累累
    0.09
    italize
    0.08
    éĨĽ
    0.08
    illed
    0.08
    ç»Ĩå¿ĥ
    0.08
     chance
    0.08
    ap
    0.08
    иÑħ
    0.08
    èĩ¾
    0.08
    Activations Density 0.006%

    No Known Activations